<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" 
  xmlns:content="http://purl.org/rss/1.0/modules/content/" 
  xmlns:dc="http://purl.org/dc/elements/1.1/" 
  xmlns:atom="http://www.w3.org/2005/Atom" 
  xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" 
  xmlns:media="http://search.yahoo.com/mrss/">
  <channel>
    <title>todo on 行李の底に収めたり[YuWd]</title>
    <link>https://yuiga.dev/blog/en/tags/todo/</link>
    <description>Recent content in todo on 行李の底に収めたり[YuWd]</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>©2026, All Rights Reserved</copyright>
    <lastBuildDate>Tue, 10 May 2022 20:32:05 +0900</lastBuildDate>
    
        <atom:link href="https://yuiga.dev/blog/en/tags/todo/index.xml" rel="self" type="application/rss+xml" />
    

      
      <item>
        <title>【論文メモ】Rethinking the Value of Labels for Improving Class-Imbalanced Learning</title>
        <link>https://yuiga.dev/blog/en/ja/posts/rethinking_the_value_of_labels_for_improving_class-imbalanced_learning/</link>
        <pubDate>Tue, 10 May 2022 20:32:05 +0900</pubDate>
        
        <atom:modified>Tue, 10 May 2022 20:32:05 +0900</atom:modified>
        <guid>https://yuiga.dev/blog/en/ja/posts/rethinking_the_value_of_labels_for_improving_class-imbalanced_learning/</guid>
        <description>不均衡データには正と負の両方の側面がある 正の側面 性能に寄与する → 負の側面 サンプル数が多いクラスに引っ張られて決定境界が歪む → https://arxiv.org/abs/2006.07529</description>
        
        <dc:creator>YuWd (Yuiga Wada)</dc:creator>
        
        
        
        
          
            
              <category>論文</category>
            
          
            
              <category>todo</category>
            
          
            
              <category>自己教師あり学習</category>
            
          
        
        
        
          
            
          
        
      </item>
      
      <item>
        <title>【論文メモ】No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models </title>
        <link>https://yuiga.dev/blog/en/ja/posts/no_parameters_left_behind_sensitivity_guided_adaptive_learning_rate_for_training_large_transformer_models/</link>
        <pubDate>Tue, 10 May 2022 14:16:57 +0900</pubDate>
        
        <atom:modified>Tue, 10 May 2022 14:16:57 +0900</atom:modified>
        <guid>https://yuiga.dev/blog/en/ja/posts/no_parameters_left_behind_sensitivity_guided_adaptive_learning_rate_for_training_large_transformer_models/</guid>
        <description>https://arxiv.org/pdf/2202.02664.pdf</description>
        
        <dc:creator>YuWd (Yuiga Wada)</dc:creator>
        
        
        
        
          
            
              <category>論文</category>
            
          
            
              <category>todo</category>
            
          
        
        
        
          
            
          
        
      </item>
      
      <item>
        <title>【論文メモ】Should You Mask 15% in Masked Language Modeling?</title>
        <link>https://yuiga.dev/blog/en/ja/posts/should_you_mask_15_in_masked_language_modeling/</link>
        <pubDate>Tue, 10 May 2022 14:16:35 +0900</pubDate>
        
        <atom:modified>Tue, 10 May 2022 14:16:35 +0900</atom:modified>
        <guid>https://yuiga.dev/blog/en/ja/posts/should_you_mask_15_in_masked_language_modeling/</guid>
        <description>https://arxiv.org/pdf/2202.08005.pdf</description>
        
        <dc:creator>YuWd (Yuiga Wada)</dc:creator>
        
        
        
        
          
            
              <category>論文</category>
            
          
            
              <category>todo</category>
            
          
        
        
        
          
            
          
        
      </item>
      
      <item>
        <title>【論文メモ】Self-Supervised Learning for Semi-Supervised Time Series Classification</title>
        <link>https://yuiga.dev/blog/en/ja/posts/self-supervised_learning_for_semi-supervised_time_series_classification/</link>
        <pubDate>Tue, 10 May 2022 11:16:03 +0900</pubDate>
        
        <atom:modified>Tue, 10 May 2022 11:16:03 +0900</atom:modified>
        <guid>https://yuiga.dev/blog/en/ja/posts/self-supervised_learning_for_semi-supervised_time_series_classification/</guid>
        <description>https://www.ismll.uni-hildesheim.de/pub/pdfs/pakdd_shayan.pdf</description>
        
        <dc:creator>YuWd (Yuiga Wada)</dc:creator>
        
        
        
        
          
            
              <category>論文</category>
            
          
            
              <category>todo</category>
            
          
        
        
        
          
            
          
        
      </item>
      

    
  </channel>
</rss>
